mm: make swapin readahead skip over holes

Ever since abandoning the virtual scan of processes, for scalability
reasons, swap space has been a little more fragmented than before.  This
can lead to the situation where a large memory user is killed, swap space
ends up full of "holes" and swapin readahead is totally ineffective.

On my home system, after killing a leaky firefox it took over an hour to
page just under 2GB of memory back in, slowing the virtual machines down
to a crawl.

This patch makes swapin readahead simply skip over holes, instead of
stopping at them.  This allows the system to swap things back in at rates
of several MB/second, instead of a few hundred kB/second.

The checks done in valid_swaphandles are already done in
read_swap_cache_async as well, allowing us to remove a fair amount of
code.

[akpm@linux-foundation.org: fix it for page_cluster >= 32]
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Adrian Drzewiecki <z@drze.net>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 11 insertions, 65 deletions

diff --git a/mm/swap_state.c b/mm/swap_state.c
index ea6b32d6187..9d3dd3763cf 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -372,25 +372,23 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	int nr_pages;
 	struct page *page;
-	unsigned long offset;
-	unsigned long end_offset;
+	unsigned long offset = swp_offset(entry);
+	unsigned long start_offset, end_offset;
+	unsigned long mask = (1UL << page_cluster) - 1;
 
-	/*
-	 * Get starting offset for readaround, and number of pages to read.
-	 * Adjust starting address by readbehind (for NUMA interleave case)?
-	 * No, it's very unlikely that swap layout would follow vma layout,
-	 * more likely that neighbouring swap pages came from the same node:
-	 * so use the same "addr" to choose the same node for each swap read.
-	 */
-	nr_pages = valid_swaphandles(entry, &offset);
-	for (end_offset = offset + nr_pages; offset < end_offset; offset++) {
+	/* Read a page_cluster sized and aligned cluster around offset. */
+	start_offset = offset & ~mask;
+	end_offset = offset | mask;
+	if (!start_offset)	/* First page is swap header. */
+		start_offset++;
+
+	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
 						gfp_mask, vma, addr);
 		if (!page)
-			break;
+			continue;
 		page_cache_release(page);
 	}
 	lru_add_drain();	/* Push any new pages onto the LRU now */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 44595a373e4..b82c028cfcc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2288,58 +2288,6 @@ int swapcache_prepare(swp_entry_t entry)
 }
 
 /*
- * swap_lock prevents swap_map being freed. Don't grab an extra
- * reference on the swaphandle, it doesn't matter if it becomes unused.
- */
-int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
-{
-	struct swap_info_struct *si;
-	int our_page_cluster = page_cluster;
-	pgoff_t target, toff;
-	pgoff_t base, end;
-	int nr_pages = 0;
-
-	if (!our_page_cluster)	/* no readahead */
-		return 0;
-
-	si = swap_info[swp_type(entry)];
-	target = swp_offset(entry);
-	base = (target >> our_page_cluster) << our_page_cluster;
-	end = base + (1 << our_page_cluster);
-	if (!base)		/* first page is swap header */
-		base++;
-
-	spin_lock(&swap_lock);
-	if (end > si->max)	/* don't go beyond end of map */
-		end = si->max;
-
-	/* Count contiguous allocated slots above our target */
-	for (toff = target; ++toff < end; nr_pages++) {
-		/* Don't read in free or bad pages */
-		if (!si->swap_map[toff])
-			break;
-		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
-			break;
-	}
-	/* Count contiguous allocated slots below our target */
-	for (toff = target; --toff >= base; nr_pages++) {
-		/* Don't read in free or bad pages */
-		if (!si->swap_map[toff])
-			break;
-		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
-			break;
-	}
-	spin_unlock(&swap_lock);
-
-	/*
-	 * Indicate starting offset, and return number of pages to get:
-	 * if only 1, say 0, since there's then no readahead to be done.
-	 */
-	*offset = ++toff;
-	return nr_pages? ++nr_pages: 0;
-}
-
-/*
  * add_swap_count_continuation - called when a swap count is duplicated
  * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's
  * page of the original vmalloc'ed swap_map, to hold the continuation count